© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 74804
    Prev
    Next
    INDEX
    Explanations

    terms related to transportation and travel logistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /stretch
    -0.08
     ones
    -0.07
    ساÙĨ
    -0.07
     the
    -0.07
    eron
    -0.07
    .hwp
    -0.07
    ýt
    -0.06
    /of
    -0.06
     Tutor
    -0.06
    ients
    -0.06
    POSITIVE LOGITS
    kea
    0.08
    isper
    0.06
    venile
    0.06
    axies
    0.06
    KHTML
    0.06
    hevik
    0.06
    SWG
    0.06
    /stdc
    0.06
    INavigation
    0.06
    kola
    0.06
    Activations Density 0.012%

    No Known Activations